Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ance
    -0.29
    mi
    -0.28
    folk
    -0.27
    ANCE
    -0.27
    itel
    -0.26
    arts
    -0.26
    æ£ĺ
    -0.26
     hé
    -0.26
     protest
    -0.26
    (mi
    -0.26
    POSITIVE LOGITS
    ä¼ļè®®ä¸Ĭ
    0.30
    产ä¸ļéĽĨèģļ
    0.28
    好人
    0.28
    ä¼ļè®®
    0.27
    ·»
    0.27
    ulus
    0.26
    该项
    0.26
    ocrates
    0.26
    主ä¸ļ
    0.25
    èĻı
    0.25
    Act Density 0.004%

    No Known Activations